學術產出-Theses
Article View/Open
Publication Export
-
題名 基於移動平均和移動標準差的CORN專家切換策略
An CORN expert switching strategy based on moving averages and moving standard deviations作者 黃旻宜
Huang, Min-Yi貢獻者 黃子銘<br>鄭宇翔
Huang, Zhi-Min<br>ZHENG,YU-XIANG
黃旻宜
Huang, Min-Yi關鍵詞 投資組合
相關係數學習無母數方法
移動標準差
移動平均值
交叉驗證
Portfolio selection
Correlation-driven Nonparametric Learning Approach
Moving standard deviation
Moving average
Cross-validation日期 2023 上傳時間 2-Aug-2023 13:05:31 (UTC+8) 摘要 本研究著重於探討無母數學習的投資組合選擇方法，即Correlation-driven Nonparametric Learning Approach (CORN)。考慮到相關係數門檻與市場視窗選擇對策略表現的關鍵影響，我們提出了兩種策略的改進方法，包括新增辨識歷史相似資料的權重參數、基於移動平均和移動標準差視窗的專家切換策略，並基於定期交叉驗證選擇視窗組合。實證研究顯示，新引進的權重參數對投資績效確實具有影響力，但過度依賴近期數據可能導致表現不佳。在固定視窗參數的情況下，切換策略可有效地提高累積績效，而且定期進行交叉驗證更能減少策略在某些參數上表現不佳的問題，進而提升模型的穩健性。然而，我們也必須指出，在面對整個市場下跌時，這些策略同時也承受相對較大的損失。因此，在進行投資決策時，我們需要綜合考慮各種因素，並對策略的優缺點做出謹慎評估。
This research explores the Correlation-driven Nonparametric Learning Approach for portfolio selection (CORN). Considering the significant impact of the correlation coefficient threshold and market window selection on strategy performance, we propose two improvements: introducing a new weight parameter for charactering time effect, and a switching strategy based on moving average and moving standard deviation windows with parameters selected using cross validation.Empirical studies indicate that the new weight parameter impacts performance, but excessive weighting on recent historical data may result in worse performance. Under fixed window parameters, switching strategies effectively enhance cumulative performance. Applying cross-validation for parameter selection can help stabilize the performance of the strategy, increase the robustness of the model. However, during market slumps, these strategies have a higher risk of losses. Therefore, investment decision should be made carefully, taking into consideration of various factors and the pros and cons of the strategies.參考文獻 Borodin, A., El-Yaniv, R., and Gogan, V. (2004). Can we learn to beat the best stock. Journal of Artificial Intelligence Research 21:579–594.Cover, T. M. (1991). Universal portfolios. Mathematical finance, 1(1):1–29.Gaivoronski, A. A. and Stella, F. (2000). Stochastic nonstationary optimization for finding universal portfolios. Annals of Operations Research, 100:165–188.Györfi, L., Lugosi, G., and Udina, F. (2006). Nonparametric kernel-based sequential in- vestment strategies. Mathematical Finance: An International Journal of Mathematics, Statistics and Financial Economics, 16(2):337–357.Györfi, L., Udina, F., and Walk, H. (2008). Nonparametric nearest neighbor based empir- ical portfolio selection strategies. 26(2):145–157.Helmbold, D. P., Schapire, R. E., Singer, Y., and Warmuth, M. K. (1998). On-line portfolio selection using multiplicative updates. Mathematical Finance, 8(4):325–347.Huang, D., Zhou, J., Li, B., Hoi, S. C., and Zhou, S. (2016). Robust median reversion strategy for online portfolio selection. IEEE Transactions on Knowledge and Data Engineering, 28(9):2480–2493.Kelly, J. L. (1956). A new interpretation of information rate. the Bell system technical journal, 35(4):917–926.Kozat, S. S. and Singer, A. C. (2007). Universal constant rebalanced portfolios with switching. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, pages 1129–1132.Li, B. and Hoi, S. C. (2014). Online portfolio selection: A survey. ACM Computing Surveys (CSUR), 46(3):1–36.Li, B., Hoi, S. C., and Gopalkrishnan, V. (2011). CORN: Correlation-driven nonparametric learning approach for portfolio selection. ACM Transactions on Intelligent Systems and Technology (TIST), 2(3):1–29.Li, B., Hoi, S. C., Sahoo, D., and Liu, Z.-Y. (2015). Moving average reversion strategy for on-line portfolio selection. Artificial Intelligence, 222:104–123.Li, B., Hoi, S. C., Zhao, P., and Gopalkrishnan, V. (2013). Confidence weighted mean reversion strategy for online portfolio selection. ACM Transactions on Knowledge Dis- covery from Data (TKDD), 7(1):1–38.Li, B., Zhao, P., Hoi, S. C., and Gopalkrishnan, V. (2012). PAMR: Passive aggressive mean reversion strategy for portfolio selection. Machine learning, 87:221–258.Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1):77–91.Vovk, V. and Watkins, C. (1998). Universal portfolio selection. In Proceedings of theeleventh annual conference on Computational learning theory, pages 12–23. 描述 碩士
國立政治大學
統計學系
110354028資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110354028 資料類型 thesis dc.contributor.advisor 黃子銘<br>鄭宇翔 zh_TW dc.contributor.advisor Huang, Zhi-Min<br>ZHENG,YU-XIANG en_US dc.contributor.author (Authors) 黃旻宜 zh_TW dc.contributor.author (Authors) Huang, Min-Yi en_US dc.creator (作者) 黃旻宜 zh_TW dc.creator (作者) Huang, Min-Yi en_US dc.date (日期) 2023 en_US dc.date.accessioned 2-Aug-2023 13:05:31 (UTC+8) - dc.date.available 2-Aug-2023 13:05:31 (UTC+8) - dc.date.issued (上傳時間) 2-Aug-2023 13:05:31 (UTC+8) - dc.identifier (Other Identifiers) G0110354028 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/146312 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 統計學系 zh_TW dc.description (描述) 110354028 zh_TW dc.description.abstract (摘要) 本研究著重於探討無母數學習的投資組合選擇方法，即Correlation-driven Nonparametric Learning Approach (CORN)。考慮到相關係數門檻與市場視窗選擇對策略表現的關鍵影響，我們提出了兩種策略的改進方法，包括新增辨識歷史相似資料的權重參數、基於移動平均和移動標準差視窗的專家切換策略，並基於定期交叉驗證選擇視窗組合。實證研究顯示，新引進的權重參數對投資績效確實具有影響力，但過度依賴近期數據可能導致表現不佳。在固定視窗參數的情況下，切換策略可有效地提高累積績效，而且定期進行交叉驗證更能減少策略在某些參數上表現不佳的問題，進而提升模型的穩健性。然而，我們也必須指出，在面對整個市場下跌時，這些策略同時也承受相對較大的損失。因此，在進行投資決策時，我們需要綜合考慮各種因素，並對策略的優缺點做出謹慎評估。 zh_TW dc.description.abstract (摘要) This research explores the Correlation-driven Nonparametric Learning Approach for portfolio selection (CORN). Considering the significant impact of the correlation coefficient threshold and market window selection on strategy performance, we propose two improvements: introducing a new weight parameter for charactering time effect, and a switching strategy based on moving average and moving standard deviation windows with parameters selected using cross validation.Empirical studies indicate that the new weight parameter impacts performance, but excessive weighting on recent historical data may result in worse performance. Under fixed window parameters, switching strategies effectively enhance cumulative performance. Applying cross-validation for parameter selection can help stabilize the performance of the strategy, increase the robustness of the model. However, during market slumps, these strategies have a higher risk of losses. Therefore, investment decision should be made carefully, taking into consideration of various factors and the pros and cons of the strategies. en_US dc.description.tableofcontents 摘要 iAbstract ii目次 iii圖目錄 v表目錄 vii第一章 緒論 1第二章 問題設計 4第三章 文獻回顧 6第一節 Markowitz投資組合理論 6第二節 線上投資組合選擇 62.1 基準Benchmarks 72.2 跟隨贏家Follow-the-Winner 82.3 跟隨輸家Follow-the-Loser 92.4 模型匹配方法Pattern-Matching Approaches 11第四章 研究方法 13第一節 研究動機 13第二節 相關係數學習無母數投資組合 15第三節 新增CORN歷史相似集的權重參數θ 16第四節 以移動標準差和移動平均視窗的切換策略 17第五節 交叉驗證選擇視窗組合的切換策略 19第六節 演算法 206.1 固定移動標準差和移動平均的切換策略 206.2 交叉驗證選擇移動標準差和移動平均的切換策略 20第五章 實證結果 23第一節 資料來源 23第二節 累積績效評估 242.1 原始 CORN 累積績效評估 252.2 CORN 新增θ累積績效評估 282.3 固定視窗組合之切換策略累積績效評估 312.4 交叉驗證篩選視窗組合之切換策略累積績效評估 38第三節 風險指標評估 433.1 夏普比率 433.2 最大回撤率 46第六章 結論與建議 49參考文獻 51 zh_TW dc.format.extent 3803364 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110354028 en_US dc.subject (關鍵詞) 投資組合 zh_TW dc.subject (關鍵詞) 相關係數學習無母數方法 zh_TW dc.subject (關鍵詞) 移動標準差 zh_TW dc.subject (關鍵詞) 移動平均值 zh_TW dc.subject (關鍵詞) 交叉驗證 zh_TW dc.subject (關鍵詞) Portfolio selection en_US dc.subject (關鍵詞) Correlation-driven Nonparametric Learning Approach en_US dc.subject (關鍵詞) Moving standard deviation en_US dc.subject (關鍵詞) Moving average en_US dc.subject (關鍵詞) Cross-validation en_US dc.title (題名) 基於移動平均和移動標準差的CORN專家切換策略 zh_TW dc.title (題名) An CORN expert switching strategy based on moving averages and moving standard deviations en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Borodin, A., El-Yaniv, R., and Gogan, V. (2004). Can we learn to beat the best stock. Journal of Artificial Intelligence Research 21:579–594.Cover, T. M. (1991). Universal portfolios. Mathematical finance, 1(1):1–29.Gaivoronski, A. A. and Stella, F. (2000). Stochastic nonstationary optimization for finding universal portfolios. Annals of Operations Research, 100:165–188.Györfi, L., Lugosi, G., and Udina, F. (2006). Nonparametric kernel-based sequential in- vestment strategies. Mathematical Finance: An International Journal of Mathematics, Statistics and Financial Economics, 16(2):337–357.Györfi, L., Udina, F., and Walk, H. (2008). Nonparametric nearest neighbor based empir- ical portfolio selection strategies. 26(2):145–157.Helmbold, D. P., Schapire, R. E., Singer, Y., and Warmuth, M. K. (1998). On-line portfolio selection using multiplicative updates. Mathematical Finance, 8(4):325–347.Huang, D., Zhou, J., Li, B., Hoi, S. C., and Zhou, S. (2016). Robust median reversion strategy for online portfolio selection. IEEE Transactions on Knowledge and Data Engineering, 28(9):2480–2493.Kelly, J. L. (1956). A new interpretation of information rate. the Bell system technical journal, 35(4):917–926.Kozat, S. S. and Singer, A. C. (2007). Universal constant rebalanced portfolios with switching. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, pages 1129–1132.Li, B. and Hoi, S. C. (2014). Online portfolio selection: A survey. ACM Computing Surveys (CSUR), 46(3):1–36.Li, B., Hoi, S. C., and Gopalkrishnan, V. (2011). CORN: Correlation-driven nonparametric learning approach for portfolio selection. ACM Transactions on Intelligent Systems and Technology (TIST), 2(3):1–29.Li, B., Hoi, S. C., Sahoo, D., and Liu, Z.-Y. (2015). Moving average reversion strategy for on-line portfolio selection. Artificial Intelligence, 222:104–123.Li, B., Hoi, S. C., Zhao, P., and Gopalkrishnan, V. (2013). Confidence weighted mean reversion strategy for online portfolio selection. ACM Transactions on Knowledge Dis- covery from Data (TKDD), 7(1):1–38.Li, B., Zhao, P., Hoi, S. C., and Gopalkrishnan, V. (2012). PAMR: Passive aggressive mean reversion strategy for portfolio selection. Machine learning, 87:221–258.Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1):77–91.Vovk, V. and Watkins, C. (1998). Universal portfolio selection. In Proceedings of theeleventh annual conference on Computational learning theory, pages 12–23. zh_TW
